Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phosph

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     é
    -0.07
     orgy
    -0.07
    .sync
    -0.06
    Alert
    -0.06
    ktor
    -0.06
    Council
    -0.06
     Benny
    -0.06
     застосов
    -0.06
    ")
↵
    -0.06
     reckon
    -0.06
    POSITIVE LOGITS
    .pick
    0.07
     馬
    0.07
     Flyers
    0.06
     Jason
    0.06
     Yaz
    0.06
    Paths
    0.06
    ,P
    0.06
    ारत
    0.06
     Tyto
    0.06
    ()*
    0.06
    Act Density 0.005%

    No Known Activations